Skills Runcomfy Com

skills/ace-step

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step...

skills/ai-avatar-video

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced...

skills/ai-image-generation

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits,...

skills/ai-music

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right...

skills/ai-video-generation

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1...

skills/codex-pet

We need to translate the given text from English to Bahasa Indonesia. The text describes a Codex Pet generator on RunComfy. It explains how to build a Codex-compatible spritesheet and pet.json from a single reference image, and then drop it into a specific directory. It also mentions the exact specifications of the atlas and that it calls OpenAI GPT Image 2. We must preserve product names, protocol names, URLs, numbers, technical terms. So "Codex Pet", "RunComfy", "Codex", "spritesheet.webp", "pet.json", "CODEX_HOME", "$HOME/.codex", "pets/", "1536x1872 PNG/WebP", "8 cols x 9 rows", "192x208 cells", "9 animation states", "idle", "running-right", "running-left", "waving", "jumping", "failed", "waiting", "running", "review", "OpenAI GPT Image 2" should remain as is or with proper capitalization. Also "Codex Pet

skills/controlnet-pose

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on...

skills/elevenlabs-music-generation

Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenLabs Music turns a style description plus structured lyrics into studio-quality 44.1 kHz stereo audio — 5 seconds to 5 minutes — with section-level control (Intro / Verse / Chorus / Bridge), multilingual vocals, and commercial-friendly output. Generate a backing track, a full vocal song, a jingle, a podcast intro, a game loop, or an instrumental bed. Calls `runcomfy run...

skills/face-swap

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for...

skills/flux-2-klein

Hasilkan gambar dengan Flux 2 Klein (varian cepat sulingan Flux 2 dari Black Forest Labs) di RunComfy — dibundel dengan pola prompt terdokumentasi model tersebut sehingga skill menghasilkan output yang lebih tajam dibandingkan prompt naif terhadap model yang sama. Mendokumentasikan keunggulan Flux 2 Klein (latensi sub-detik, gaya merek multi-referensi, prompt deklaratif subjek-pertama), strategi jumlah langkah (4–8 untuk iterasi cepat, ~25 untuk polesan), trade-off varian 9B vs 4B, dan kapan harus mengarahkan ke Flux 2 Pro /...

skills/flux-kontext

Edit gambar dengan Flux 1 Kontext Pro (model edit gambar lokal presisi dari Black Forest Labs) di RunComfy — dibundel dengan pola prompting terdokumentasi model tersebut sehingga skill menghasilkan output yang lebih tajam dibandingkan prompting naif terhadap model yang sama. Mendokumentasikan keunggulan Flux Kontext (edit lokal presisi dengan satu referensi, kontrol prompt yang kuat, output fidelitas tinggi yang konsisten), skema (satu gambar + prompt), dan kapan harus beralih ke Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein. Memanggil...

skills/gpt-image-2

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any...

skills/gpt-image-edit

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls...

skills/happyhorse-1-0

We need to translate the given text from English to Bahasa Indonesia. The text is a description of an agent skill for "happyhorse-1-0". We must preserve the name "happyhorse-1-0" and other proper names like "HappyHorse 1.0", "RunComfy", "Artificial Analysis Video Arena", "Wan 2.7", "Seedance 2", "LTX 2", "RunComfy CLI", and the command string. Also preserve numbers, URLs, technical terms. Do not add any extra commentary or labels. The translation should be natural in Indonesian. Let's break down the text: "Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX

skills/image-edit

Edit gambar di RunComfy — skill ini adalah router pintar yang mencocokkan niat pengguna dengan model edit yang tepat di katalog RunComfy. Memilih Nano Banana Edit (batch hingga 20, identitas default yang terjaga), OpenAI GPT Image 2 Edit (penulisan ulang teks dalam gambar multibahasa, komposisi multi-referensi, presisi tata letak), Flux Kontext Pro (edit lokal high-fidelity referensi tunggal), atau Z-Image Turbo Inpaint (edit wilayah presisi berbasis mask). Menggabungkan pola prompt terdokumentasi setiap model sehingga skill mendapatkan...

skills/image-inpainting

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the...

skills/image-outpainting

We need to translate the given text from English to Bahasa Indonesia, preserving the specified terms: "image-outpainting", "RunComfy", "runcomfy", "Nano Banana 2 Edit", "GPT Image 2 Edit", "FLUX Kontext Pro", "Seedream", "Dreamina", "Qwen", "FLUX 2". Also preserve URLs, numbers, technical terms. Do not add any extra commentary or labels. The text is a description of an agent skill. Translate only the content inside <text>. The name "image-outpainting" is not in the source text? Actually it is in the first line: "Image outpainting on RunComfy..." So we need to translate "Image outpainting" but preserve the name? The instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "Image outpainting" might be a technical term, but it's also the name of the skill. The instruction says "Do not include the name unless it appears in the source text." It does

skills/image-to-video

We need to translate the given text from English to Bahasa Indonesia. The text describes a skill called "image-to-video" but the instruction says not to include the name unless it appears in the source text. The name "image-to-video" does appear in the source? Actually the source text starts with "Animate any still image on RunComfy — this skill is a smart router..." The name is not explicitly written as "image-to-video" in the source text. The directory item type is "agent skill" and the name to preserve is "image-to-video". But the instruction says: "Do not include the name unless it appears in the source text." The name "image-to-video" does not appear in the source text. So we should not add it. We just translate the text inside <text>. We need to preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7",

skills/kling-3-0

Pembuatan video Kling 3.0 di RunComfy. Kling 3.0 (juga disebut Kling V3.0) adalah model video multi-shot generasi ketiga dari Kuaishou Technology dengan audio sinkron asli dan identitas karakter yang konsisten antar shot. Skill ini mencakup keenam endpoint Kling 3.0, mencakup tiga tingkatan rendering (Standard, Pro, 4K) dan dua mode (teks-ke-video, gambar-ke-video). Panggilan runcomfy run kling/kling-3.0/ / melalui CLI RunComfy lokal. Dipicu oleh "kling", "kling 3.0", "kling v3", "kling pro",...

skills/lipsync

We need to translate the given English text into Indonesian. The text describes a skill for lip-syncing. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "lipsync" is not in the text? Actually it appears as "Lip-sync" at the beginning. The instruction says "Do not include the name unless it appears in the source text." The name "lipsync" appears as "Lip-sync" in the source text. So we should translate that as well? But the instruction says "Preserve product names" and "Name to preserve: lipsync". So we should keep "lipsync" as is? But the source has "Lip-sync" with hyphen and capital L. Probably we should keep it as "Lip-sync" or "lipsync"? The instruction says "Name to preserve: lipsync" (lowercase). But in the text it's "Lip-sync". I think we should preserve the exact form as in the source: "Lip-sync". However, the instruction says

skills/nano-banana-2

Hasilkan gambar dengan Google Nano Banana 2 (text-to-image tingkat flash keluarga Gemini) di RunComfy — dibundel dengan pola prompt terdokumentasi model tersebut sehingga skill menghasilkan output yang lebih tajam dibandingkan prompt naif terhadap model yang sama. Mendokumentasikan keunggulan Nano Banana 2 (iterasi cepat, rendering tipografi dalam gambar, pembingkaian yang dapat diprediksi, konteks berbasis web opsional), harga berdasarkan tingkat resolusi, dial toleransi keamanan, serta kapan harus beralih ke Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

skills/nano-banana-edit

Edit gambar dengan Google Nano Banana 2 (endpoint edit gambar-ke-gambar) di RunComfy. Mendokumentasikan kelebihan Nano Banana Edit (mempertahankan identitas subjek,

skills/relight

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....

skills/runcomfy-cli

We need to translate the given English text into Bahasa Indonesia. The text describes a CLI tool called runcomfy-cli (name preserved). The instruction says to translate only the text inside <text>, not include the name unless it appears in source. The name "runcomfy-cli" is not in the source text; the source mentions "runcomfy CLI" but not "runcomfy-cli". However, the directory item type is "agent skill" and name to preserve is "runcomfy-cli". But the instruction says "Do not include the name unless it appears in the source text." The source text has "runcomfy CLI" (with space) not "runcomfy-cli". So we should not add "runcomfy-cli" in the translation. We'll translate the text as is, preserving "runcomfy CLI" as a proper name. Also preserve URLs, numbers, technical terms. The text has "ControlNet", "LoRA", etc. Keep them as is. Translate: "Run any model on RunComfy

skills/seedance-v2

Hasilkan video pendek sinematik dengan ByteDance Seedance 2.0 Pro di RunComfy. Mendokumentasikan keunggulan Seedance 2.0 Pro (referensi multimodal — hingga 9 gambar, 3 video, 3 audio — audio tersinkronisasi dalam video dengan lip-sync alami, penyempurnaan

skills/video-edit

Edit video yang sudah ada di RunComfy — skill ini adalah router pintar yang mencocokkan maksud pengguna dengan model edit yang tepat di katalog RunComfy. Memilih Wan 2.7 Edit-Video (restyle umum / tukar latar belakang / tukar kemasan, preservasi identitas + gerakan), Kling 2.6 Pro Motion Control (transfer gerakan presisi dari video referensi ke karakter target), atau Lucy Edit Restyle (restyle ringan dengan preservasi identitas / tukar pakaian). Menggabungkan pola prompt terdokumentasi setiap model sehingga skill...

skills/video-extend

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

skills/video-inpainting

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

skills/video-outpainting

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand...

skills/wan-2-7

We need to translate the given text from English to Bahasa Indonesia. The text describes an agent skill for generating text-to-video using Wan 2.7. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "wan-2-7" is to be preserved if it appears in the source text. The instruction says: "Do not include the name unless it appears in the source text." The name appears multiple times: "Wan 2.7", "wan-2-7", "wan". So we keep those as is. Also "RunComfy", "HappyHorse 1.0", "Seedance 2.0", "Kling", "LTX 2", "CLI", "audio_url", "runcomfy run wan-ai/wan-2-7/text-to-video" are technical terms/names to preserve. We translate the rest naturally. Let's break down the text: "Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model